| 1 | // RUN: %clang_cc1 -triple spir-unknown-unknown -cl-std=CL2.0 -emit-llvm %s -O0 -o - | FileCheck %s |
|---|
| 2 | |
|---|
| 3 | typedef __attribute__(( ext_vector_type(2) )) int int2; |
|---|
| 4 | typedef __attribute__(( ext_vector_type(4) )) int int4; |
|---|
| 5 | |
|---|
| 6 | // CHECK: %struct.StrucTy = type { i32, i32, i32 } |
|---|
| 7 | |
|---|
| 8 | // CHECK: @GA = addrspace(1) global [6 x [6 x float]] {{[[][[]}}6 x float] [float 1.000000e+00, float 2.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00], |
|---|
| 9 | // CHECK: [6 x float] zeroinitializer, [6 x float] zeroinitializer, [6 x float] zeroinitializer, [6 x float] zeroinitializer, [6 x float] zeroinitializer], align 4 |
|---|
| 10 | float GA[6][6] = {1.0f, 2.0f}; |
|---|
| 11 | |
|---|
| 12 | typedef struct { |
|---|
| 13 | int x; |
|---|
| 14 | int y; |
|---|
| 15 | int z; |
|---|
| 16 | } StrucTy; |
|---|
| 17 | |
|---|
| 18 | // CHECK: @GS = addrspace(1) global %struct.StrucTy { i32 1, i32 2, i32 0 }, align 4 |
|---|
| 19 | StrucTy GS = {1, 2}; |
|---|
| 20 | |
|---|
| 21 | // CHECK: @GV1 = addrspace(1) global <4 x i32> <i32 1, i32 2, i32 3, i32 4>, align 16 |
|---|
| 22 | int4 GV1 = (int4)((int2)(1,2),3,4); |
|---|
| 23 | |
|---|
| 24 | // CHECK: @GV2 = addrspace(1) global <4 x i32> <i32 1, i32 1, i32 1, i32 1>, align 16 |
|---|
| 25 | int4 GV2 = (int4)(1); |
|---|
| 26 | |
|---|
| 27 | // CHECK: @__const.f.S = private unnamed_addr addrspace(2) constant %struct.StrucTy { i32 1, i32 2, i32 0 }, align 4 |
|---|
| 28 | |
|---|
| 29 | // CHECK-LABEL: define spir_func void @f() |
|---|
| 30 | void f(void) { |
|---|
| 31 | // CHECK: %[[A:.*]] = alloca [6 x [6 x float]], align 4 |
|---|
| 32 | // CHECK: %[[S:.*]] = alloca %struct.StrucTy, align 4 |
|---|
| 33 | // CHECK: %[[V1:.*]] = alloca <4 x i32>, align 16 |
|---|
| 34 | // CHECK: %[[compoundliteral:.*]] = alloca <4 x i32>, align 16 |
|---|
| 35 | // CHECK: %[[compoundliteral1:.*]] = alloca <2 x i32>, align 8 |
|---|
| 36 | // CHECK: %[[V2:.*]] = alloca <4 x i32>, align 16 |
|---|
| 37 | |
|---|
| 38 | // CHECK: %[[v0:.*]] = bitcast [6 x [6 x float]]* %A to i8* |
|---|
| 39 | // CHECK: call void @llvm.memset.p0i8.i32(i8* align 4 %[[v0]], i8 0, i32 144, i1 false) |
|---|
| 40 | // CHECK: %[[v1:.*]] = bitcast i8* %[[v0]] to [6 x [6 x float]]* |
|---|
| 41 | // CHECK: %[[v2:.*]] = getelementptr inbounds [6 x [6 x float]], [6 x [6 x float]]* %[[v1]], i32 0, i32 0 |
|---|
| 42 | // CHECK: %[[v3:.*]] = getelementptr inbounds [6 x float], [6 x float]* %[[v2]], i32 0, i32 0 |
|---|
| 43 | // CHECK: store float 1.000000e+00, float* %[[v3]], align 4 |
|---|
| 44 | // CHECK: %[[v4:.*]] = getelementptr inbounds [6 x float], [6 x float]* %[[v2]], i32 0, i32 1 |
|---|
| 45 | // CHECK: store float 2.000000e+00, float* %[[v4]], align 4 |
|---|
| 46 | float A[6][6] = {1.0f, 2.0f}; |
|---|
| 47 | |
|---|
| 48 | // CHECK: %[[v5:.*]] = bitcast %struct.StrucTy* %S to i8* |
|---|
| 49 | // CHECK: call void @llvm.memcpy.p0i8.p2i8.i32(i8* align 4 %[[v5]], i8 addrspace(2)* align 4 bitcast (%struct.StrucTy addrspace(2)* @__const.f.S to i8 addrspace(2)*), i32 12, i1 false) |
|---|
| 50 | StrucTy S = {1, 2}; |
|---|
| 51 | |
|---|
| 52 | // CHECK: store <2 x i32> <i32 1, i32 2>, <2 x i32>* %[[compoundliteral1]], align 8 |
|---|
| 53 | // CHECK: %[[v6:.*]] = load <2 x i32>, <2 x i32>* %[[compoundliteral1]], align 8 |
|---|
| 54 | // CHECK: %[[vext:.*]] = shufflevector <2 x i32> %[[v6]], <2 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef> |
|---|
| 55 | // CHECK: %[[vecinit:.*]] = shufflevector <4 x i32> %[[vext]], <4 x i32> undef, <4 x i32> <i32 0, i32 1, i32 undef, i32 undef> |
|---|
| 56 | // CHECK: %[[vecinit2:.*]] = insertelement <4 x i32> %[[vecinit]], i32 3, i32 2 |
|---|
| 57 | // CHECK: %[[vecinit3:.*]] = insertelement <4 x i32> %[[vecinit2]], i32 4, i32 3 |
|---|
| 58 | // CHECK: store <4 x i32> %[[vecinit3]], <4 x i32>* %[[compoundliteral]], align 16 |
|---|
| 59 | // CHECK: %[[v7:.*]] = load <4 x i32>, <4 x i32>* %[[compoundliteral]], align 16 |
|---|
| 60 | // CHECK: store <4 x i32> %[[v7]], <4 x i32>* %[[V1]], align 16 |
|---|
| 61 | int4 V1 = (int4)((int2)(1,2),3,4); |
|---|
| 62 | |
|---|
| 63 | // CHECK: store <4 x i32> <i32 1, i32 1, i32 1, i32 1>, <4 x i32>* %[[V2]], align 16 |
|---|
| 64 | int4 V2 = (int4)(1); |
|---|
| 65 | } |
|---|
| 66 | |
|---|
| 67 | |
|---|